Mastodawn

Before diving into deep learning hype, remember the power of classic algorithms. Linear regression, decision trees, and thoughtful feature engineering still drive real‑world analytics and revenue. Master these fundamentals and your neural nets will perform better, faster, and cheaper. Curious how the basics outpace the buzz? Read on. #NeuralNetworks #LinearRegression #DecisionTrees #FeatureEngineering

🔗 https://aidailypost.com/news/master-fundamentals-before-neural-networks-core-algorithms-power

Show thread

Eric Maugendre about data Nov 19

"It is not uncommon for an analyst to conduct a supervised analysis of data to detect which predictors are significantly associated with the outcome. These significant predictors are then used in a visualization (such as a heat map or cluster analysis) on the same data. Not surprisingly, the visualization reliably demonstrates clear patterns between the outcomes and predictors and appears to provide evidence of their importance. However, since the same data are shown, the visualization is essentially cherry picking the results that are only true for these data and which are unlikely to generalize to new data."

Wrote Max Kuhn @topepo and Kjell Johnson, 2019, in "Feature Engineering and Selection: A Practical Approach for Predictive Models" https://bookdown.org/max/FES/

#correlations #NoFreeLunch #electricity #agriculture #livestock #renewables #dataViz #emissions #GHG #methane #GreenhouseForcing #dataScience #featureEngineering #correlation

Show thread

bayo Nov 19

𝟓/𝟓⁣
Data quality = AI quality. What's your biggest data transformation challenge?⁣
⁣
Like/Repost if you're building data pipelines! 🔁⁣
⁣
#DataEngineering #TimescaleDB #FeatureEngineering #MLOps

AI Daily Post Nov 18

Want to catch hidden seasonality and drift in your data? Plotting timestamps reveals trends, class‑imbalance shifts, and lets you build a robust feature set for production models. Our latest research shows how temporal patterns boost performance—open‑source tools included. Dive in to see the visual tricks that keep your ML pipelines ahead. #TemporalPatterns #Seasonality #FeatureEngineering #ModelProduction

🔗 https://aidailypost.com/news/use-temporal-patterns-plot-timestamps-spot-seasonality-trends-shifts

aicoder Nov 7

#AIEngineering #featureengineering #cheatsheet

https://machinelearningmastery.com/10-python-one-liners-for-calculating-model-feature-importance/

10 Python One-Liners for Calculating Model Feature Importance - MachineLearningMastery.com

10 simple but effective Python one-liners to calculate model feature importance from different perspectives, enabling not only understanding of how your machine learning model behaves, but also why it predicts the way it does.

MachineLearningMastery.com

HackerNoon Sep 13

Speed up XGBoost training by 46x with one parameter change. Learn how GPU acceleration saves hours, boosts iteration, and scales to big data.
https://hackernoon.com/stop-waiting-make-xgboost-46x-faster-with-one-parameter-change #featureengineering

Stop Waiting: Make XGBoost 46x Faster With One Parameter Change | HackerNoon

Speed up XGBoost training by 46x with one parameter change. Learn how GPU acceleration saves hours, boosts iteration, and scales to big data.

HackerNoon Aug 22

Discover how we built a zero-ops, serverless feature engineering platform on Google Cloud using BigQuery, Dataflow, and Vertex AI. https://hackernoon.com/building-a-lambda-style-feature-platform-with-gcp-native-services #featureengineering

Building a Lambda-Style Feature Platform with GCP Native Services | HackerNoon

Discover how we built a zero-ops, serverless feature engineering platform on Google Cloud using BigQuery, Dataflow, and Vertex AI.

Jesus Castagnetto 🇵🇪Aug 16

"Basic Feature Engineering with #DuckDB"

#ML #FeatureEngineering

https://duckdb.org/2025/08/15/ml-data-preprocessing.html

Basic Feature Engineering with DuckDB

In this post, we show how to perform essential machine learning data preprocessing tasks, like missing value imputation, categorical encoding, and feature scaling, directly in DuckDB using SQL. This approach not only simplifies workflows, but also takes advantage of DuckDB’s high-performance, in-process execution engine for fast, efficient data preparation.

DuckDB

aicoder Jul 12

#AIEngineering #featureengineering #Dataprep

Word Embeddings for Tabular Data Feature Engineering

https://machinelearningmastery.com/word-embeddings-for-tabular-data-feature-engineering/